doc-page-extractor 0.0.6__tar.gz → 0.0.7__tar.gz

{doc_page_extractor-0.0.6 → doc_page_extractor-0.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: doc-page-extractor
-Version: 0.0.6
+Version: 0.0.7
 Summary: doc page extractor can identify text and format in images and return structured data.
 Home-page: https://github.com/Moskize91/doc-page-extractor
 Author: Tao Zeyu
@@ -10,7 +10,6 @@ License-File: LICENSE
 Requires-Dist: opencv-python<5.0,>=4.11.0
 Requires-Dist: pillow<11.0,>=10.3
 Requires-Dist: pyclipper<2.0,>=1.2.0
-Requires-Dist: onnxruntime<2.0,>=1.19.0
 Requires-Dist: numpy<2.0,>=1.24.0
 Requires-Dist: shapely<3.0,>=2.0.0
 Requires-Dist: transformers<5.0,>=4.48.0
@@ -37,10 +36,20 @@ doc page extractor can identify text and format in images and return structured
 pip install doc-page-extractor
 ```
 
+```shell
+pip install onnxruntime==1.21.0
+```
+
 ## Using CUDA
 
 Please refer to the introduction of [PyTorch](https://pytorch.org/get-started/locally/) and select the appropriate command to install according to your operating system.
 
+In addition, replace the command to install `onnxruntime` in the previous article with the following:
+
+```shell
+pip install onnxruntime-gpu==1.21.0
+```
+
 ## Example
 
 ```python
@@ -49,7 +58,7 @@ from doc_page_extractor import DocExtractor
 
 extractor = DocExtractor(
   model_dir_path=model_path, # Folder address where AI model is downloaded and installed
-  device="cpu", # If you want to use CUDA, please change to device="cuda:0".
+  device="cpu", # If you want to use CUDA, please change to device="cuda".
 )
 with Image.open("/path/to/your/image.png") as image:
   result = extractor.extract(

{doc_page_extractor-0.0.6 → doc_page_extractor-0.0.7}/README.md

@@ -12,10 +12,20 @@ doc page extractor can identify text and format in images and return structured
 pip install doc-page-extractor
 ```
 
+```shell
+pip install onnxruntime==1.21.0
+```
+
 ## Using CUDA
 
 Please refer to the introduction of [PyTorch](https://pytorch.org/get-started/locally/) and select the appropriate command to install according to your operating system.
 
+In addition, replace the command to install `onnxruntime` in the previous article with the following:
+
+```shell
+pip install onnxruntime-gpu==1.21.0
+```
+
 ## Example
 
 ```python
@@ -24,7 +34,7 @@ from doc_page_extractor import DocExtractor
 
 extractor = DocExtractor(
   model_dir_path=model_path, # Folder address where AI model is downloaded and installed
-  device="cpu", # If you want to use CUDA, please change to device="cuda:0".
+  device="cpu", # If you want to use CUDA, please change to device="cuda".
 )
 with Image.open("/path/to/your/image.png") as image:
   result = extractor.extract(

{doc_page_extractor-0.0.6 → doc_page_extractor-0.0.7}/doc_page_extractor/extractor.py

@@ -1,5 +1,4 @@
 import os
-import torch
 
 from typing import Literal, Iterable
 from pathlib import Path
@@ -34,10 +33,6 @@ class DocExtractor:
     self._yolo: YOLOv10 | None = None
     self._layout: LayoutLMv3ForTokenClassification | None = None
 
-    if self._device.startswith("cuda") and not torch.cuda.is_available():
-      self._device = "cpu"
-      print("Warn: cuda is not available, use cpu instead")
-
   def extract(
       self,
       image: Image,
@@ -83,7 +78,7 @@ class DocExtractor:
       source=source,
       imgsz=1024,
       conf=0.2,
-      device=self._device    # Device to use (e.g., "cuda:0" or "cpu")
+      device=self._device    # Device to use (e.g., "cuda" or "cpu")
     )
     boxes = det_res[0].__dict__["boxes"]
     layouts: list[Layout] = []

{doc_page_extractor-0.0.6 → doc_page_extractor-0.0.7}/doc_page_extractor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: doc-page-extractor
-Version: 0.0.6
+Version: 0.0.7
 Summary: doc page extractor can identify text and format in images and return structured data.
 Home-page: https://github.com/Moskize91/doc-page-extractor
 Author: Tao Zeyu
@@ -10,7 +10,6 @@ License-File: LICENSE
 Requires-Dist: opencv-python<5.0,>=4.11.0
 Requires-Dist: pillow<11.0,>=10.3
 Requires-Dist: pyclipper<2.0,>=1.2.0
-Requires-Dist: onnxruntime<2.0,>=1.19.0
 Requires-Dist: numpy<2.0,>=1.24.0
 Requires-Dist: shapely<3.0,>=2.0.0
 Requires-Dist: transformers<5.0,>=4.48.0
@@ -37,10 +36,20 @@ doc page extractor can identify text and format in images and return structured
 pip install doc-page-extractor
 ```
 
+```shell
+pip install onnxruntime==1.21.0
+```
+
 ## Using CUDA
 
 Please refer to the introduction of [PyTorch](https://pytorch.org/get-started/locally/) and select the appropriate command to install according to your operating system.
 
+In addition, replace the command to install `onnxruntime` in the previous article with the following:
+
+```shell
+pip install onnxruntime-gpu==1.21.0
+```
+
 ## Example
 
 ```python
@@ -49,7 +58,7 @@ from doc_page_extractor import DocExtractor
 
 extractor = DocExtractor(
   model_dir_path=model_path, # Folder address where AI model is downloaded and installed
-  device="cpu", # If you want to use CUDA, please change to device="cuda:0".
+  device="cpu", # If you want to use CUDA, please change to device="cuda".
 )
 with Image.open("/path/to/your/image.png") as image:
   result = extractor.extract(

{doc_page_extractor-0.0.6 → doc_page_extractor-0.0.7}/doc_page_extractor.egg-info/requires.txt

@@ -1,7 +1,6 @@
 opencv-python<5.0,>=4.11.0
 pillow<11.0,>=10.3
 pyclipper<2.0,>=1.2.0
-onnxruntime<2.0,>=1.19.0
 numpy<2.0,>=1.24.0
 shapely<3.0,>=2.0.0
 transformers<5.0,>=4.48.0

{doc_page_extractor-0.0.6 → doc_page_extractor-0.0.7}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
   name="doc-page-extractor",
-  version="0.0.6",
+  version="0.0.7",
   author="Tao Zeyu",
   author_email="i@taozeyu.com",
   url="https://github.com/Moskize91/doc-page-extractor",
@@ -14,7 +14,6 @@ setup(
     "opencv-python>=4.11.0,<5.0",
     "pillow>=10.3,<11.0",
     "pyclipper>=1.2.0,<2.0",
-    "onnxruntime>=1.19.0,<2.0",
     "numpy>=1.24.0,<2.0",
     "shapely>=2.0.0,<3.0",
     "transformers>=4.48.0,<5.0",